# Timestamp: 2026-08-22T01:02:43.579934+00:00
# Git SHA: 0a1b3e0a15d67d551041933529c2c41032f5b28d
# World size: 4
# speculators: 0.7.0.dev194
# vllm: 0.25.1
# transformers: 5.14.1
# torch: 2.11.0
# compressed-tensors: 0.17.0
scripts/train.py --verifier-name-or-path Qwen/Qwen3-4B --speculator-type dflash2 --data-path /home/shanjiaz/Qwen3-4B-preprocessed --vllm-endpoint http://localhost:8000/v1 --save-path ./output/dflash2_qwen3_4b_8spec/checkpoints --block-size 9 --max-anchors 512 --num-layers 5 --target-layer-ids 1 9 17 25 33 --conv-kernel-size 2 --conv-group-size 16 --selector-rank 256 --selector-top-k 16 --loss-fn '{"ce": 0.1, "tv": 0.9}' --dflash-decay-gamma 4.0 --per-position-loss-weight fixed-exp-decay --optimizer adamw --lr 6e-4 --weight-decay 0.0 --scheduler-type cosine --scheduler-warmup-ratio 0.04 --epochs 1 --total-seq-len 8192 --seed 42 --fsdp-shard --on-missing generate --on-generate delete --checkpoint-freq 0.1